DTP medical advice automatic notification method and system based on short message triggering

Abstract

The invention provides a DTP medical advice automatic notification method and system based on short message triggering, and belongs to the technical field of DTP medical advice automatic notification. The method comprises the following steps: verifying and synchronizing subject information according to subject data, monitoring transition of a prescription state and generating a trigger event; calling a preset message template library, and matching to obtain a corresponding first short message content and an acceptance role; the subject information is processed based on a predefined label rule base, a patient portrait label is constructed, and a doctor advice notification risk score of a patient is calculated; and according to the patient portrait label and the patient medical advice notification risk score, adjusting the first short message content to obtain a second short message content, and according to the determined short message notification mode, touching the second short message content to the accepting role to complete DTP medical advice automatic notification. According to the invention, through a state driving mechanism, mode change from passive waiting to active triggering is realized. The optimal notification strategy is intelligently matched by fusing patient portraits, testee ages and the like.

Description

Technical Field

[0001] This invention relates to the field of DTP (Direct-to-Patient) medical order automatic notification technology, specifically to a DTP medical order automatic notification method and system based on SMS triggering. Background Technology

[0002] In the field of clinical trials, ensuring that subjects can obtain and take investigational drugs in a timely and accurate manner is a core aspect of guaranteeing the reliability of trial data and the safety of medication use for subjects. With the evolution of drug development models, the DTP (Direct to Patient) model, as a new drug management model that delivers investigational drugs directly to subjects, is gaining increasing attention due to its ability to improve subject accessibility and enhance the trial participation experience. The efficient operation of this model heavily relies on seamless collaboration and real-time data exchange between the in-hospital Clinical Trial Management System (CTMS) as the command center and the pharmacy DTP system as the drug supply execution terminal.

[0003] However, under the current technological architecture, CTMS and DTP systems are often heterogeneous systems built independently and implemented in phases, creating system barriers between them. At the data flow level, critical trial information, subject profiles, and prescription data cannot be automatically and in real-time synchronized between the systems, still heavily relying on research nurses or project administrators to manually perform data synchronization operations, essentially building a data bridge between the systems that requires manual maintenance. At the business process level, there is a break in this critical link from prescription approval in CTMS to the generation of a dispensing order and triggering patient notification in DTP. Currently, the process often requires pharmacists or nurses to manually query and generate dispensing orders in the DTP system to drive subsequent steps. This deep reliance on manual operation not only introduces the risk of process interruptions due to human error or delays but also makes the entire notification process lagging, failing to automatically trigger notifications immediately upon changes in prescription status, severely restricting the efficiency and response speed of clinical trials. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for automatic notification of DTP medical orders based on SMS triggering, which can realize the full-process automated management of clinical trial DTP medical orders from prescription status changes to personalized notification delivery, and improve medication safety and operational efficiency through intelligent triggering and precise adaptation.

[0005] To achieve the above objectives, this invention provides a method for automatic DTP (Direct-to-Patient) prescription notification based on SMS triggering, comprising: collecting subject data; verifying and synchronizing subject information based on the subject data; monitoring prescription status transitions and generating trigger events; based on the trigger events, calling a preset message template library to match and obtain corresponding first SMS content and receiving roles; processing subject information based on a predefined tag rule library to construct patient profile tags and calculate a patient prescription notification risk score; adjusting the first SMS content based on the patient profile tags and the patient prescription notification risk score to obtain second SMS content and determining the SMS notification method; and delivering the second SMS content to the receiving role according to the determined SMS notification method to complete the automatic DTP prescription notification.

[0006] Optionally, the collection of subject data, and the verification and synchronization of subject information based on the subject data, include: obtaining subject information from the clinical trial management system through a predefined application programming interface using a polling or listening mechanism; the subject information includes project patient master data and prescription order data; performing format verification and business rule verification on the obtained project patient master data and prescription order data; and persistently storing the subject information in a local database after both the format verification and the business rule verification pass.

[0007] Optionally, monitoring prescription status transitions and generating trigger events includes: monitoring predefined state transitions of prescription business entities through a state machine model; the predefined state transitions include prescription data being successfully downloaded from the clinical trial management system to the DTP system, the prescription being successfully delivered to the patient, the patient information submission timeout being determined, and the review status of the associated medication application changing; when any of the predefined state transition events is detected, the state machine model generates a structured trigger event message and delivers the trigger event message to the event bus for asynchronous distribution.

[0008] Optionally, the matching to obtain the corresponding first SMS content and receiving role includes: parsing the triggering event, extracting the event type identifier and the unique identifier corresponding to the business object encapsulated in the triggering event message; using the event type identifier as a query key to query the predefined mapping relationship between event types and templates in the preset message template library to locate and determine the corresponding target message template; retrieving the corresponding subject information from the associated clinical data source according to the unique identifier; injecting the retrieved subject information into the target message template to generate the first SMS content and determine the corresponding receiving role.

[0009] Optionally, the step of processing subject information and constructing patient profile tags based on a predefined tag rule base includes: extracting raw data of predefined categories from the subject information, wherein the predefined categories include demographic attributes, disease diagnosis information, and historical medication behavior records; inputting the raw data of the predefined categories into a predefined tag rule base, wherein the predefined tag rule base contains tag generation rules defined by conditional logic statements; and converting the raw data of the predefined categories into patient profile tags by executing the tag generation rules, wherein the patient profile tags include at least basic tags, behavioral tags, and risk tags.

[0010] Optionally, calculating the patient's medical order notification risk score includes: converting a subset of risk labels in the patient profile labels into a machine-readable feature vector; inputting the feature vector into a pre-trained medical order notification risk assessment model, which is constructed based on a machine learning algorithm; and using the medical order notification risk assessment model to perform forward reasoning on the feature vector to obtain the patient's medical order notification risk score.

[0011] Optionally, adjusting the content of the first SMS message to obtain the content of the second SMS message and determining the SMS notification method includes: inputting the patient profile tag and the patient's medical order notification risk score as input conditions into the strategy matching module of the outreach engine; having the strategy matching module query a preset outreach strategy library and match the corresponding content optimization strategy and notification channel strategy; modifying the content of the first SMS message according to the content optimization strategy to generate the second SMS message content; and determining the SMS notification method including the main channel and auxiliary channels according to the notification channel strategy.

[0012] Optionally, the matching logic of the outreach strategy library includes: when the patient profile tag indicates that the patient's age is greater than or equal to the set age for older patients, the matching notification channel strategy is a dual-channel strategy of SMS and AI voice call, and the matching content optimization strategy includes simplification of voice content and speech rate control; when the patient profile tag indicates that the patient's age is less than or equal to the set age for younger patients, the matching notification channel strategy is a linkage strategy of SMS and mini-program pop-up, and the matching content optimization strategy includes attaching a one-click jump link in the SMS; when the patient's medical order notification risk score indicates high risk, the matching content optimization strategy further includes adding risk warning information to the first SMS content, and the matching notification channel strategy adds the research nurse as a collaborative notification role.

[0013] Optionally, the step of delivering the second SMS content to the recipient role according to the determined SMS notification method includes: encapsulating the second SMS content, the recipient role, and the SMS notification method into a standardized notification task message; distributing the notification task message to the corresponding message processing interface according to the communication channel type specified in the SMS notification method; and calling the corresponding communication service through the message processing interface to deliver the second SMS content to the recipient role.

[0014] On the other hand, the present invention provides a DTP (Direct-to-Patient) medical order automatic notification system triggered by SMS, for implementing a DTP medical order automatic notification method triggered by SMS. The system includes a control module, the control module including a memory, a processor and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the DTP medical order automatic notification method triggered by SMS.

[0015] The aforementioned technical solution, through a state-driven mechanism, senses key milestones in the prescription workflow in real time (such as download, review, and timeout), enabling a shift from passive waiting to proactive triggering. By integrating patient profiles and subject age, it generates a patient medical order notification risk score and intelligently matches the optimal notification strategy (such as SMS, voice, and mini-program linkage), significantly improving the accuracy and effectiveness of information delivery.

[0016] Other features and advantages of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the following detailed description to explain the invention, but do not constitute a limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of the DTP (Direct-to-Patient) automatic notification process triggered by SMS.

[0019] Figure 2 This is a flowchart of the decision-making process for personalized patient outreach strategies. Detailed Implementation

[0020] The following is in conjunction with the appendix Figure 1 - Appendix Figure 2 The specific implementation methods of the embodiments of the present invention will be described in detail below. It should be understood that the specific implementation methods described herein are only for illustrating and explaining the embodiments of the present invention, and are not intended to limit the embodiments of the present invention.

[0021] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0022] In the process of realizing this invention, the inventors of this application discovered that the prior art has the defects of high dependence on manual operation, data isolation between systems, and breakpoints in business processes, resulting in low efficiency and delayed response of clinical trial DTP medical order notification.

[0023] Example 1

[0024] Reference Figures 1-2 This is the first embodiment of the present invention, which provides a method for automatic notification of DTP medical orders triggered by SMS, including:

[0025] S100: Collect subject data, verify and synchronize subject information based on subject data, monitor prescription status transitions and generate trigger events.

[0026] In the embodiments of this application, subject information is obtained from the clinical trial management system through a predefined application programming interface using a polling or listening mechanism. The subject information includes project patient master data and prescription order data. Format validation and business rule validation are performed on the obtained project patient master data and prescription order data. After both format validation and business rule validation pass, the subject information is persistently stored in the local database.

[0027] In a preferred embodiment of this application, subject data is collected in real time from the Clinical Trial Management System (CTMS) using a predefined application programming interface (API) employing both polling and listening modes. Data collection covers multi-dimensional information, including patient master data and prescription data. Patient master data includes demographic attributes (age, gender), disease diagnosis information, enrollment status, and historical records; prescription data includes key prescription information such as drug name, specifications, dosage, frequency of administration, date of prescription, and prescribing physician.

[0028] Preferably, the subject information also includes project metadata, which includes basic information such as the project's unique number, the trial protocol version number, and the study period.

[0029] Furthermore, the synchronization process for subject data employs an asynchronous communication model, using a message queue to buffer data flow. This effectively decouples the source and target systems, preventing performance pressure on either side during synchronization. The collected raw subject data then undergoes two levels of verification to ensure the accuracy and compliance of the incoming data.

[0030] The two levels of validation described above are format validation and business rule validation. Format validation includes structural verification of data fields, such as whether the date is in YYYY-MM-DD format, whether the field length meets constraints, and whether the encoding is standardized. Format validation quickly filters out low-level format errors. Business rule validation is a deep semantic validation that ensures the data conforms to the business logic of clinical trials. For example, it verifies whether the drugs involved in the prescription have been officially activated and their master data maintained under the current trial project to prevent invalid or unauthorized drug orders from being generated, and verifies whether the prescription issuer (investigation physician) is on the project personnel list and has the correct permissions.

[0031] Following the example above, any verification failure will trigger the system's alarm mechanism, record detailed error logs, and notify relevant personnel to intervene and handle the issue. The data will be temporarily stored in an isolation area to await repair.

[0032] In a preferred embodiment of this application, the patient master data is written into the patient master file table, and the prescription order data is entered into the prescription order management table, establishing a relationship with the master data of projects, institutions, drugs, etc. Importantly, the prescription record will contain a dynamic "status" field (such as "pending issuance", "issued", "pending review", etc.), which is the direct object of subsequent state machine monitoring.

[0033] In the embodiments of this application, a state machine model is used to monitor the predefined state transitions of prescription business entities. The predefined state transitions include the successful download of prescription data from the clinical trial management system to the DTP system, the successful delivery of the prescription to the patient, the determination that the patient information submission has timed out, and the change of the review status of the associated medication application. When any predefined state transition event is detected, the state machine model generates a structured trigger event message and delivers the trigger event message to the event bus for asynchronous distribution.

[0034] It should be noted that the state machine model is an intelligent process control engine based on finite state machine theory, specifically designed for DTP (Direct-to-Patient) medical order automatic notification systems. It achieves real-time monitoring and automated driving of clinical trial medication processes by clearly defining the state space of prescription business entities (including six core states: pending synchronization, received, issued, pending review, completed, and abnormal state), event sets (such as data synchronization completion, outbound order generation, patient operation timeout, etc.), and state transition rules (for example, when a prescription is successfully downloaded from the CTMS system to the DTP system, the state transitions from "pending synchronization" to "received", and an SMS notification is automatically triggered).

[0035] Preferably, this state machine model uses an event-driven architecture to ensure that each state change can accurately trigger the corresponding business operation (such as sending an SMS). At the same time, it has built-in timing monitoring and exception handling mechanisms (such as automatic warning for patient information submission timeout), which effectively improves process reliability and response efficiency. Its deep integration with the DTP system makes the medical order notification process highly controllable and adaptive.

[0036] Furthermore, the DTP system captures state transition signals generated by business operations in real time by deploying an asynchronous event listener cluster. When a state transition is detected and confirmed, the DTP system generates a structured trigger event message containing a unique message identifier, a precise timestamp, and a digital signature. The trigger event message is asynchronously distributed through the event bus.

[0037] The above solution collects data from the CTMS system in real time through a dual-mode API polling and monitoring, ensuring that subject information and prescription orders can be synchronized to the DTP system, thus solving the problem of information silos. Through the state machine model, it can automatically and accurately identify key nodes in the prescription lifecycle, replacing manual screen monitoring or periodic checks, and achieving 24 / 7 uninterrupted monitoring. Once a state transition is detected, a trigger event is automatically generated to drive subsequent processes, significantly improving efficiency and reducing human error.

[0038] S200: Based on the triggered event, call the preset message template library to match and obtain the corresponding first SMS content and the receiving role.

[0039] In a preferred embodiment of this application, message format verification is first performed to ensure the integrity and compliance of event data. The parser extracts core metadata such as event type identifiers, unique identifiers for business objects, and timestamp sequences, and transforms the discrete event data into feature vectors with clear business semantics through feature extraction algorithms.

[0040] Preferably, the DTP system has a pre-defined message template library, which predefines the mapping relationship between various event types and message templates. After obtaining the event type identifier, the DTP system uses it as the query key to perform exact matching in the message template library. The matching process employs a multi-level retrieval strategy: first, exact matching is performed; when multiple candidate templates exist, optimization is then performed based on business scenario characteristics. The template matching comprehensively considers factors including: the matching degree of the event type, the relevance of the business scenario, and the timeliness of the template. Through a weighted evaluation model, the applicability score of each candidate template is calculated, and the target message template is finally selected.

[0041] Furthermore, based on the unique identifier of the business object, complete subject information is retrieved from associated clinical data sources. The data retrieval process employs a distributed query mechanism, enabling efficient access to multiple data storage nodes. First, the basic profile information of the subject is located, and then the retrieval is expanded to include relevant clinical trial data, medication records, and other business information. The retrieved subject information is then standardized. After standardization, the retrieved subject information is injected into the target message template to generate the first SMS message content. Simultaneously, a role mapping model is used to determine the corresponding recipient role.

[0042] The above solution, through a pre-set message template library, ensures that SMS messages sent to different roles (subjects, research nurses, etc.) are formatted consistently, use standardized language, and contain complete information. This avoids ambiguity or missing information that may arise from manual drafting, thus improving professional image and communication quality. The DTP system can automatically match the corresponding receiving role based on the event type (such as new medical orders, shipping notifications) and automatically retrieve relevant information from the database to populate the template. This process requires no manual judgment or searching, ensuring that the right information is sent to the right person at the right time, thereby reducing errors and omissions in the communication chain.

[0043] S300: Processes subject information based on a predefined label rule base, constructs patient profile labels, and calculates patient medical order notification risk scores.

[0044] In the embodiments of this application, raw data of predefined categories are extracted from subject information. The predefined categories include demographic attributes, disease diagnosis information, and historical medication behavior records. The raw data of the predefined categories are input into a predefined label rule base, which contains label generation rules defined by conditional logic statements. By executing the label generation rules, the raw data of the predefined categories are transformed into patient profile labels. The patient profile labels include at least basic labels, behavioral labels, and risk labels.

[0045] In a preferred embodiment of this application, the predefined tag rule base adopts a layered architecture design, including a basic rule layer, a business rule layer, and a risk rule layer. The basic rule layer handles static attributes such as demographics, the business rule layer analyzes dynamic information such as medication behavior, and the risk rule layer focuses on generating risk assessment indicators. The tag generation process uses rule engine technology to transform raw data into structured tags through conditional logic judgments. The DTP system supports multiple rule types, including threshold rules, trend rules, and association rules. Each tag undergoes multiple verifications to ensure its accuracy and reliability. The generated tag system includes three layers: basic tags, behavioral tags, and risk tags, forming a complete patient profile.

[0046] Calculating the patient's medical order notification risk score includes: converting a subset of risk labels from the patient profile tags into a machine-readable feature vector; inputting the feature vector into a pre-trained medical order notification risk assessment model, which is built based on a machine learning algorithm; and using the medical order notification risk assessment model to perform forward inference on the feature vector to obtain the patient's medical order notification risk score.

[0047] Preferably, the machine learning algorithm includes a feature input layer, multiple hidden layers, and a result output layer. The inference process uses a forward propagation algorithm to calculate feature transformations layer by layer, ultimately outputting a patient's medical order notification risk score.

[0048] The above approach identifies individuals requiring special attention from group management through patient profile tags. Based on a machine learning model, the risk score for patient medical order notification transforms risk judgments that previously relied on subjective experience into quantifiable indicators. This allows the DTP system to identify patients with high dropout or medication safety risks in advance, thereby prioritizing limited clinical management resources for the subjects who need the most attention, achieving precision medicine and proactive risk management.

[0049] S400: Based on the patient profile tags and the patient's medical order notification risk score, adjust the content of the first SMS message to obtain the content of the second SMS message, and determine the SMS notification method.

[0050] In the embodiments of this application, patient profile tags and patient medical order notification risk scores are used as input conditions and input into the strategy matching module of the outreach engine; the strategy matching module queries the preset outreach strategy library and matches the corresponding content optimization strategy and notification channel strategy; according to the content optimization strategy, the content of the first SMS message is modified to generate the content of the second SMS message; according to the notification channel strategy, the SMS notification method including the main channel and the auxiliary channel is determined.

[0051] In a preferred embodiment of this application, the outreach engine is the core decision-making module of the DTP system, with a built-in strategy matching module and outreach strategy library. The strategy matching process through the strategy matching module adopts rule engine technology, which compares the characteristics of the input data (such as patient age and risk level) with the conditional rules in the outreach strategy library in real time to locate the optimal content optimization strategy and notification channel strategy.

[0052] In a preferred embodiment of this application, when the patient profile tag indicates that the patient's age is greater than or equal to the set age for older patients, the matching notification channel strategy is a dual-channel strategy of SMS and AI voice call, and the matching content optimization strategy includes simplification of voice content and control of speech rate; when the patient profile tag indicates that the patient's age is less than or equal to the set age for younger patients, the matching notification channel strategy is a linkage strategy of SMS and mini-program pop-up window, and the matching content optimization strategy includes adding a one-click jump link in the SMS; when the patient's medical order notification risk score indicates high risk, the matching content optimization strategy also includes adding risk warning information to the first SMS content, and the matching notification channel strategy adds the research nurse as a collaborative notification role.

[0053] Further optimized, when the patient profile tag indicates that the patient is 65 years of age or older, a dual-protection notification mechanism is activated. The main channel uses traditional SMS notification to ensure the reliability of basic information transmission; the auxiliary channel uses an AI voice call system to enhance information delivery through voice broadcasting. The AI ​​voice call system can recognize the patient's dialect and supports multilingual broadcasting, and activates an automatic redial mechanism when the call is not connected to ensure information delivery to the greatest extent possible.

[0054] The voice content simplification process employs hierarchical compression technology to transform complex medical information into easily understandable everyday language, automatically removing technical jargon and replacing abstract descriptions with concrete action instructions. For example, "Please take your medication on time" is optimized to "Please remember to take the white pill after meals every day." The speech rate control system sets broadcast parameters according to the patient's age group: a moderate speech rate of 120 words per minute for the 65-75 age group, and a further reduced rate of 90 words per minute for the over 75 age group, with appropriate pauses inserted at key information points.

[0055] When the patient profile tag indicates that the patient is 40 years of age or older, the main channel uses rich media SMS, supporting mixed text and images and the use of emojis; the auxiliary channel enables WeChat mini-program pop-up notifications and is deeply integrated with the hospital's official mini-program. One-click redirect links use deep linking technology, allowing patients to directly jump to a specific page in the mini-program, such as a medication guidance page or a medication record page. Link generation uses a dynamically parameterized design, supporting personalized content pre-filling to reduce user operation steps.

[0056] When the patient is not in the above age range (65 years or older or 40 years or younger), standard SMS should be used as the notification method, and the content of the first SMS should be used as the content of the second SMS.

[0057] When a patient's risk score in a medical order notification exceeds a set risk score threshold (not a fixed number, but an adjustable business rule parameter; different clinical trial projects have different risk tolerance levels for patient medication safety due to the characteristics of their investigational drugs, therefore each project may set its own risk score threshold), the patient's medical order notification risk score indicates high risk. The DTP system embeds multi-level risk warning information into the basic SMS content, using a color-coding system: red indicates urgent risks, and orange indicates important reminders. The warning content includes a detailed risk description, coping measures, and emergency contact information, along with a QR code that the patient can scan to watch a detailed risk explanation video. Research nurses intervene as co-notifiers, simultaneously receiving patient risk information and contact details, and supporting one-click dialing and quick replies using message templates. The DTP system automatically creates a tracking task list.

[0058] The above solution can dynamically adjust the notification channel and content based on the patient profile, fully considering the acceptance ability and usage habits of different user groups, ensuring that key medication information can be effectively received and understood. When the patient's medical order notification risk score is higher than the set risk score threshold, not only is the prompt content optimized, but the research nurse is also automatically added as a collaborative notification role, establishing a collaborative guarantee mechanism of system early warning plus manual intervention, ensuring that high-risk situations can be followed up by timely and professional human intervention.

[0059] S500: Following the established SMS notification method, the second SMS message is sent to the recipient to complete the automatic notification of DTP medical orders.

[0060] In the embodiments of this application, the second SMS content, the receiving role, and the SMS notification method are encapsulated into a standardized notification task message; the notification task message is distributed to the corresponding message processing interface according to the communication channel type specified in the SMS notification method; and the corresponding communication service is called through the message processing interface to deliver the second SMS content to the receiving role.

[0061] In a preferred embodiment of this application, the encapsulation process adopts a layered structure design, converting business data into a processable standardized message format. The encapsulation layer comprises three core components: a metadata header, a message body, and a transmission control section. The metadata header records the message generation timestamp, a unique message identifier, etc. The message body stores the second SMS content using structured encoding, supporting multiple formats such as plain text and rich media. The transmission control section includes transmission control information such as detailed information on the receiving role, retry policy parameters, and validity period settings. The encapsulation process uses digital signature technology to ensure message integrity and prevent content tampering. The routing engine analyzes the receiver's role characteristics and channel characteristics based on a pre-configured routing table to select the optimal message processing interface. For SMS channels, messages are distributed to the SMS gateway interface; for AI voice channels, messages are routed to the speech synthesis interface; for mini-program notifications, messages are sent to the WeChat Official Accounts Platform interface, automatically switching to a backup channel when the primary channel is unavailable.

[0062] Preferably, the routing process records detailed logs, including the basis for routing decisions, distribution timestamps, and interface response status. The DTP system executes communication services through an asynchronous call model, continuously tracking the delivery status after a message is sent and receiving status reports from the communication service provider via callback interfaces. For important notifications, end-user confirmation of receipt is required.

[0063] The present invention also provides a DTP (Direct-to-Patient) medical order automatic notification system triggered by SMS, for implementing a DTP medical order automatic notification method triggered by SMS. The system includes a control module, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the DTP medical order automatic notification method triggered by SMS.

[0064] This invention provides a storage medium storing a program that, when executed by a processor, implements the SMS-triggered DTP automatic medical order notification method.

[0065] This invention provides a processor for running a program, wherein the program executes the SMS-triggered DTP automatic medical order notification method during runtime.

[0066] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements a method for automatic DTP (Direct-to-Patient) medical order notification triggered by SMS. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0067] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing a DTP (Direct-to-Patient) automatic notification method based on SMS triggering.

[0068] Those skilled in the art will understand that embodiments of this application can provide methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0073] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0074] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0075] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0076] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for automatic notification of DTP medical orders triggered by SMS, characterized in that, include: Collect subject data, verify and synchronize subject information based on the subject data, monitor the transition of prescription status and generate trigger events; Based on the triggering event, a preset message template library is invoked to match and obtain the corresponding first SMS content and the receiving role; Subject information is processed based on a predefined label rule base to construct patient profile labels and calculate patient medical order notification risk scores; Based on the patient profile tags and the patient medical order notification risk score, adjust the content of the first SMS message to obtain the content of the second SMS message, and determine the SMS notification method; According to the determined SMS notification method, the second SMS message content is sent to the recipient role to complete the automatic notification of DTP medical orders.

2. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 1, characterized in that, The process of collecting subject data, verifying and synchronizing subject information based on the subject data, includes: Subject information, including project patient master data and prescription order data, is obtained from the clinical trial management system through a predefined application programming interface using a polling or listening mechanism. Perform format validation and business rule validation on the acquired patient master data and prescription order data. After both the format verification and the business rule verification pass, the subject information is persistently stored in the local database.

3. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 1, characterized in that, The monitoring of prescription status transitions and generation of trigger events includes: Monitor the predefined state transitions of prescription business entities using a state machine model; The predefined state transitions include: prescription data being successfully transmitted from the clinical trial management system to the DTP system; the prescription being successfully sent to the patient; the patient information submission timeout being determined; and the review status of the associated medication application changing. When any of the predefined state transition events is detected, the state machine model generates a structured trigger event message and delivers the trigger event message to the event bus for asynchronous distribution.

4. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 3, characterized in that, The matching process yields the corresponding first SMS message content and the recipient's role, including: The triggering event is parsed to extract the event type identifier and the unique identifier corresponding to the business object encapsulated in the triggering event message; Using the event type identifier as a query key, the predefined mapping relationship between event types and templates is queried in the preset message template library to locate and determine the corresponding target message template; Based on the unique identifier, the corresponding subject information is retrieved from the associated clinical data source; The retrieved subject information is injected into the target message template to generate the first SMS content, and the corresponding recipient role is determined.

5. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 1, characterized in that, The process of processing subject information based on a predefined label rule base to construct patient profile labels includes: Raw data for predefined categories are extracted from subject information, including demographic attributes, disease diagnosis information, and historical medication behavior records. The raw data of the predefined category is input into a predefined tag rule library, which contains tag generation rules defined by conditional logic statements; By executing the label generation rules, the raw data of the predefined categories are transformed into patient profile labels, which include at least basic labels, behavioral labels, and risk labels.

6. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 1, characterized in that, The calculation of the patient medical order notification risk score includes: Convert the risk label subset in the patient profile label into a machine-readable feature vector; The feature vector is input into a pre-trained medical order notification risk assessment model, which is built based on a machine learning algorithm. The patient's medical order notification risk score is obtained by forward reasoning on the feature vector using the aforementioned medical order notification risk assessment model.

7. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 1, characterized in that, The process of adjusting the content of the first SMS message to obtain the content of the second SMS message and determining the SMS notification method includes: The patient profile tags and the patient medical order notification risk score are used together as input conditions and input into the strategy matching module of the outreach engine. The strategy matching module queries the preset reach strategy library and matches the corresponding content optimization strategy and notification channel strategy. Based on the content optimization strategy, the content of the first SMS message is modified to generate the content of the second SMS message; Based on the notification channel strategy, the SMS notification method, which includes a main channel and an auxiliary channel, is determined.

8. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 7, characterized in that, The matching logic of the reach strategy library includes: When the patient profile label indicates that the patient's age is greater than or equal to the set age for older patients, the matching notification channel strategy is a dual-channel strategy of SMS and AI voice call, and the matching content optimization strategy includes simplification of voice content and control of speech rate. When the patient profile tag indicates that the patient's age is less than or equal to the set young patient age, the matching notification channel strategy is a linkage strategy of SMS and mini-program pop-up, and the matching content optimization strategy includes attaching a one-click jump link in the SMS. When the patient's medical order notification risk score indicates a high risk, the matching content optimization strategy also includes adding risk warning information to the first SMS message content, and the matching notification channel strategy adds the research nurse as a collaborative notification role.

9. The method for automatic notification of DTP medical orders based on SMS triggering according to claim 1, characterized in that, The step of delivering the second SMS message to the recipient role according to the determined SMS notification method includes: The second SMS content, the receiving role, and the SMS notification method are encapsulated into a standardized notification task message; According to the communication channel type specified in the SMS notification method, the notification task message is distributed to the corresponding message processing interface; The message processing interface is used to call the corresponding communication service to deliver the second SMS message to the recipient.

10. A DTP (Direct-to-Patient) medical order automatic notification system triggered by SMS, characterized in that, The system includes a control module, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the SMS-triggered automatic notification method for DTP medical orders according to any one of claims 1-9.

Images